mcpscore AGENTS.md

Repository instructions for mcpscore, a tool that checks MCP servers against the MCP specification. They define required validation commands and rules for creating, versioning, scoping, and retiring checks.

In plain words
What is it for?
Use them when adding or changing mcpscore rules, documentation, tests, or validation behavior.
Why use it?
They prevent changes from breaking the project’s tests or changing stable rule identifiers and explain how specification changes should be handled.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/mcp-box/mcpscore/agents-md
Clone the repo
git clone --depth 1 https://github.com/mcp-box/mcpscore

Made for: Codex, OpenCode.

Per session 1,268 This file is loaded in full into every session.
When invoked 1,268 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01268 $0.01268
Opus 5 $0.00634 $0.00634
Sonnet 5 $0.00254 $0.00254
Haiku 4.5 $0.00127 $0.00127

Measured 3d ago against content hash 0615f9d85010, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcpscore AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent instructions for mcpscore

  • Run make all before handing off — it mirrors CI (lint, typecheck, tests + coverage). The gate is uv run pyright mcpscore/ and uv run ruff check — inline IDE diagnostics may differ; the commands are authoritative.
  • rule_id is a stable public contract: never rename or reuse one. New rules must cite the MCP spec section (or SEP) they enforce in their result details.
  • Rule lifecycle — three states, and the choice between them matters:
    1. Active — runs everywhere.
    2. Version-scoped — set min_spec_version/max_spec_version when a rule is correct but only for some revisions. Use this for anything the spec removed or deprecated: the rule keeps its ID and still judges servers on the revisions where the requirement held. Obsolescence is scoping, not deletion.
    3. Retired — delete the rule only when it was wrong (it asserted something the spec does not require, or contradicted another rule), and add an entry to mcpscore/rules/retired.py. That registry generates the "Retired rules" table in docs/rules.mdx, so an old report or a stale CI waiver stays explainable. A retired ID is never reused — a test enforces it.
  • Readiness rules (group_name = "readiness") score on the readiness axis; since the 1.1.0 promotion they ALSO count in the main score, but only for modern-lifecycle servers (era modern/dual-era) in full audits — never for legacy servers, never in partial audits (readiness_promoted in mcp_auditor.py is the single switch). Rules that cannot judge anything return a skip reason — they never fail a server for missing observations.
  • Probes must never invoke tools/call against a target server — audits must be free of tool side effects. Probes never raise; network failures are ProbeOutcome.ERROR data.
  • docs/rules.mdx is generated — edit scripts/generate_rules_doc.py and run make docs-rules, never the file itself. CI fails on drift.
  • Docs are MDX served by Mintlify from docs/ — pages need frontmatter; validate with make docs-check.
  • For each new feature: update the docs and add a CHANGELOG entry (Keep a Changelog format). Docstrings: imperative first line, ≤120-char lines.
  • Do not commit to main; work on a branch. Do not add strategy or planning documents to this repository — it is public.
  • docs-live is a deploy pointer, never a working branch — and never delete it (nor main; both are deletion-protected by repository rulesets since 2026-08-27). Mintlify serves docs.mcpscore.dev from docs-live; publish-docs.yml force-pushes it to each stable release tag. Deleting it takes the docs site down; committing to it gets overwritten at the next release. Docs changes go through main like everything else and reach the site at the next release.

Read the full file on GitHub · 71 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 71 lines · 1,268 tokens per session scan A 0615f9d85010

Subscribe to this mod's changes

mcpscore AGENTS.md is an instructions file published in the GitHub repository mcp-box/mcpscore (29 stars, last pushed 3d ago), licensed MIT. It adds 1,268 tokens to every session, about $0.0063 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

vector_mcp AGENTS.md

AGENTS.md instructions for sergiobayona/vector_mcp, covering agents.md, project overview, essential commands, development setup and testing and quality.

sergiobayona/vector_mcp · 4,505 tokens

Genesis-World-MCP AGENTS.md

AGENTS.md instructions for Gnidreve/Genesis-World-MCP, covering agents.md — cas genesisworld mcp, what this is, standing orders — read first, design pillars and source layout & conventions.

Gnidreve/Genesis-World-MCP · 7,868 tokens

pixabay-mcp-server CLAUDE.md

Claude Code instructions for hanoak/pixabay-mcp-server, covering claude.md, project overview, tech stack (decided — do not relitigate without discussion), architecture & folder conventions and coding standards.

hanoak/pixabay-mcp-server · 3,594 tokens

youtube-studio-mcp AGENTS.md

AGENTS.md instructions for hygef-v4/youtube-studio-mcp: When the user requests software development, software architecture, new features, or modifications, ALWAYS read and follow CLAUDE.md to execute the AI-DLC workflow.

hygef-v4/youtube-studio-mcp · 49 tokens

atelier-mcp copilot-instructions.md

Copilot instructions for anshrajore/atelier-mcp, covering run npm run sync-adapters to update, universal ui/ux rules, universal backend architecture rules and framework presets (available in skills/atelier/presets/).

anshrajore/atelier-mcp · 496 tokens

xc-mcp CLAUDE.md

Claude Code instructions for conorluddy/xc-mcp, covering claude.md, project overview, architecture (v4.0.0), v4.0 migration guide (breaking) and development commands.

conorluddy/xc-mcp · 5,635 tokens